{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:32:54Z","timestamp":1777570374729,"version":"3.51.4"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200465","type":"print"},{"value":"9783031200472","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20047-2_7","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T10:02:55Z","timestamp":1666432975000},"page":"112-128","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Towards Generic 3D Tracking in\u00a0RGBD Videos: Benchmark and\u00a0Baseline"],"prefix":"10.1007","author":[{"given":"Jinyu","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongqun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyung Jin","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ale\u0161","family":"Leonardis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Ahmadyan, A., Zhang, L., Ablavatski, A., Wei, J., Grundmann, M.: Objectron: a large scale dataset of object-centric videos in the wild with pose annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7822\u20137831 (2021)","DOI":"10.1109\/CVPR46437.2021.00773"},{"key":"7_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional Siamese networks for object tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Bibi, A., Zhang, T., Ghanem, B.: 3D part-based sparse tracker with automatic synchronization and registration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1439\u20131448 (2016)","DOI":"10.1109\/CVPR.2016.160"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Chen, W., Jia, X., Chang, H.J., Duan, J., Shen, L., Leonardis, A.: FS-Net: fast shape-based network for category-level 6d object pose estimation with decoupled rotation mechanism. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1581\u20131590 (2021)","DOI":"10.1109\/CVPR46437.2021.00163"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: Minkowski convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3075\u20133084 (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Comport, A.I., Marchand, \u00c9., Chaumette, F.: Robust model-based tracking for robot vision. In: 2004 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)(IEEE Cat. No. 04CH37566), vol. 1, pp. 692\u2013697. IEEE (2004)","DOI":"10.1109\/IROS.2004.1389433"},{"key":"7_CR8","unstructured":"Cui, Y., Fang, Z., Shan, J., Gu, Z., Zhou, S.: 3D object tracking with transformer. arXiv preprint arXiv:2110.14921 (2021)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Ericson, C.: Real-Time Collision Detection. CRC Press, Boca Raton (2004)","DOI":"10.1201\/b14581"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The Kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Giancola, S., Zarzar, J., Ghanem, B.: Leveraging shape completion for 3D Siamese tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00145"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Kart, U., Lukezic, A., Kristan, M., Kamarainen, J.K., Matas, J.: Object tracking by reconstruction with view-specific discriminative correlation filters. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1339\u20131348 (2019)","DOI":"10.1109\/CVPR.2019.00143"},{"key":"7_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"7_CR14","doi-asserted-by":"publisher","unstructured":"Kristan, M., et al.: The eighth visual object tracking VOT2020 challenge results. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12539, pp. 547\u2013601. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-68238-5_39","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"7_CR15","unstructured":"Kristan, M., et al.: The seventh visual object tracking VOT2019 challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)"},{"key":"7_CR16","unstructured":"Kristan, M., et al.: The ninth visual object tracking vot2021 challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2711\u20132738 (2021)"},{"key":"7_CR17","doi-asserted-by":"publisher","unstructured":"Li, E., Wang, S., Li, C., Li, D., Wu, X., Hao, Q.: SUSTech points: a portable 3D point cloud interactive annotation platform system. In: 2020 IEEE Intelligent Vehicles Symposium (IV), pp. 1108\u20131115 (2020). https:\/\/doi.org\/10.1109\/IV47402.2020.9304562","DOI":"10.1109\/IV47402.2020.9304562"},{"key":"7_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/978-3-030-58542-6_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Liao","year":"2020","unstructured":"Liao, B., Wang, C., Wang, Y., Wang, Y., Yin, J.: PG-Net: pixel to global matching network for visual tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 429\u2013444. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_26"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Lukezic, A., et al.: CDTB: a color and depth visual object tracking dataset and benchmark. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10013\u201310022 (2019)","DOI":"10.1109\/ICCV.2019.01011"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Luo, W., Yang, B., Urtasun, R.: Fast and furious: real time end-to-end 3D detection, tracking and motion forecasting with a single convolutional net. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3569\u20133577 (2018)","DOI":"10.1109\/CVPR.2018.00376"},{"key":"7_CR21","unstructured":"Machida, E., Cao, M., Murao, T., Hashimoto, H.: Human motion tracking of mobile robot with Kinect 3D sensor. In: 2012 Proceedings of SICE Annual Conference (SICE), pp. 2207\u20132211. IEEE (2012)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3D object detection in point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"7_CR23","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. arXiv preprint arXiv:1706.02413 (2017)"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Qi, H., Feng, C., Cao, Z., Zhao, F., Xiao, Y.: P2b: point-to-box network for 3D object tracking in point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.00636"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: SUN RGB-D: A RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Song, S., Xiao, J.: Tracking revisited using RGBD camera: unified benchmark and baselines. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 233\u2013240 (2013)","DOI":"10.1109\/ICCV.2013.36"},{"key":"7_CR27","doi-asserted-by":"publisher","unstructured":"Taylor, C., McNicholas, R., Cosker, D.: Towards an egocentric framework for rigid and articulated object tracking in virtual reality. In: 2020 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), pp. 354\u2013359 (2020). https:\/\/doi.org\/10.1109\/VRW50115.2020.00077","DOI":"10.1109\/VRW50115.2020.00077"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6D object pose and size estimation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00275"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xie, Q., Lai, Y.K., Wu, J., Long, K., Wang, J.: MLVSNet: multi-level voting Siamese network for 3D visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3101\u20133110 (2021)","DOI":"10.1109\/ICCV48922.2021.00309"},{"issue":"8","key":"7_CR30","doi-asserted-by":"crossref","first-page":"2485","DOI":"10.1109\/TCYB.2017.2740952","volume":"48","author":"J Xiao","year":"2017","unstructured":"Xiao, J., Stolkin, R., Gao, Y., Leonardis, A.: Robust fusion of color and depth data for RGB-D target tracking using adaptive range-invariant depth models and spatio-temporal consistency constraints. IEEE Trans. Cybern. 48(8), 2485\u20132499 (2017)","journal-title":"IEEE Trans. Cybern."},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Yan, S., Yang, J., Kapyla, J., Zheng, F., Leonardis, A., Kamarainen, J.K.: DepthTrack: unveiling the power of RGBD tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10725\u201310733 (2021)","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Yan, X., Zheng, C., Li, Z., Wang, S., Cui, S.: PointASNL: robust point clouds processing using nonlocal neural networks with adaptive sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5589\u20135598 (2020)","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Zheng, C., et al.: Box-aware feature enhancement for single object tracking on point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13199\u201313208 (2021)","DOI":"10.1109\/ICCV48922.2021.01295"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Zou, H., et al.: F-Siamese tracker: a frustum-based double Siamese network for 3D single object tracking. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8133\u20138139. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341120"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20047-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T10:02:33Z","timestamp":1728208953000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20047-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200465","9783031200472"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20047-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}